<html>
<head>
<meta http-equiv="Content-Type" content="text/html; charset=utf-8">
</head>
<body>
<div style="font-family: Tahoma, Geneva, sans-serif; font-size: 14pt; color: rgb(0, 0, 0);">
<b><i>"Scalable Learning with Probabilistic PCA"</i></b></div>
<div class="elementToProof" style="font-family: Tahoma, Geneva, sans-serif; font-size: 12pt; color: rgb(0, 0, 0);">
<br>
</div>
<div class="elementToProof" style="font-family: Tahoma, Geneva, sans-serif; font-size: 14pt; color: rgb(0, 0, 0);">
<b>Adrian Barbu</b></div>
<div class="elementToProof" style="font-family: Tahoma, Geneva, sans-serif; font-size: 12pt; color: rgb(0, 0, 0);">
Department of Statistics, Florida State University</div>
<div class="elementToProof" style="font-family: Tahoma, Geneva, sans-serif; font-size: 12pt; color: rgb(0, 0, 0);">
<br>
</div>
<div class="elementToProof" style="font-family: Tahoma, Geneva, sans-serif; font-size: 12pt; color: rgb(0, 0, 0);">
Please feel free to forward/share this invitation with other groups/disciplines that might be interested in this talk/topic.
<b>All are welcome to attend. </b></div>
<div style="font-family: Tahoma, Geneva, sans-serif; font-size: 12pt; color: rgb(0, 0, 0);">
<br>
</div>
<div style="font-family: Tahoma, Geneva, sans-serif; font-size: 12pt; color: rgb(0, 0, 0);">
NOTE: <b>In-person attendance is requested in our 499 Dirac Science Library (DSL) Seminar Room.</b> Zoom access is intended for external (non-departmental) participants only. </div>
<div class="elementToProof" style="font-family: Tahoma, Geneva, sans-serif; font-size: 12pt; color: rgb(0, 0, 0);">
<br>
</div>
<div style="font-family: Tahoma, Geneva, sans-serif; font-size: 12pt; color: rgb(0, 0, 0);">
<b>https://fsu.zoom.us/j/94273595552 </b></div>
<div class="elementToProof" style="font-family: Tahoma, Geneva, sans-serif; font-size: 12pt; color: rgb(0, 0, 0);">
Meeting #<b> 942 7359 5552 </b></div>
<div style="font-family: Tahoma, Geneva, sans-serif; font-size: 12pt; color: rgb(0, 0, 0);">
<br>
</div>
<div class="elementToProof" style="font-family: Tahoma, Geneva, sans-serif; font-size: 12pt; color: rgb(0, 0, 0);">
🎦 Colloquium recordings will be made available here, <a href="https://nam04.safelinks.protection.outlook.com/?url=https%3A%2F%2Fwww.sc.fsu.edu%2Fcolloquium&data=05%7C02%7Csc-seminar-announce%40lists.fsu.edu%7Cee7743f828d5455dbf6b08dd4219d171%7Ca36450ebdb0642a78d1b026719f701e3%7C0%7C0%7C638739400828235727%7CUnknown%7CTWFpbGZsb3d8eyJFbXB0eU1hcGkiOnRydWUsIlYiOiIwLjAuMDAwMCIsIlAiOiJXaW4zMiIsIkFOIjoiTWFpbCIsIldUIjoyfQ%3D%3D%7C0%7C%7C%7C&sdata=ALejqfr6e52DSXvOpvaU2ZTrBfBqzc3R0y4fT%2BZRqHg%3D&reserved=0" originalsrc="https://www.sc.fsu.edu/colloquium" shash="D3hqgRbDvxTLaWQIjqdSN+DctW19wIW2scS+JP8MT7hJ4R9zQSdbtY3GJNeUnCMLpFFKClpuTC10+3cR9rwPkIOUBZPwfq1DUl8MldvxWG3Uy0bPzbrj+G+adD/lwI/+TnMJ94UAjoGSjJAY+np4F7ge+krXWAjFc3PMc9qIbps=" id="OWA48d02544-30b4-45b5-56cf-198979f6cf54" class="OWAAutoLink">
https://www.sc.fsu.edu/colloquium</a> </div>
<div style="font-family: Tahoma, Geneva, sans-serif; font-size: 12pt; color: rgb(0, 0, 0);">
<br>
</div>
<div class="elementToProof" style="font-family: Tahoma, Geneva, sans-serif; font-size: 12pt; color: rgb(0, 0, 0);">
<b>Wednesday, Feb 5, 2025, Schedule: </b></div>
<div style="font-family: Tahoma, Geneva, sans-serif; font-size: 12pt; color: rgb(0, 0, 0);">
<br>
</div>
<div class="elementToProof" style="font-family: Tahoma, Geneva, sans-serif; font-size: 12pt; color: rgb(0, 0, 0);">
* 3:00 to 3:30 PM Eastern Time (US and Canada) </div>
<div style="font-family: Tahoma, Geneva, sans-serif; font-size: 12pt; color: rgb(0, 0, 0);">
☕ Nespresso & Teatime - 417 DSL Commons </div>
<div class="elementToProof" style="font-family: Tahoma, Geneva, sans-serif; font-size: 12pt; color: rgb(0, 0, 0);">
<br>
</div>
<div style="font-family: Tahoma, Geneva, sans-serif; font-size: 12pt; color: rgb(0, 0, 0);">
<b>* 3:30 to 4:30 PM Eastern Time (US and Canada) </b></div>
<div class="elementToProof" style="font-family: Tahoma, Geneva, sans-serif; font-size: 12pt; color: rgb(0, 0, 0);">
<b>🕟 Colloquium - 499 DSL Seminar Room </b></div>
<div class="elementToProof" style="font-family: Tahoma, Geneva, sans-serif; font-size: 12pt; color: rgb(0, 0, 0);">
<br>
</div>
<div style="font-family: Tahoma, Geneva, sans-serif; font-size: 12pt; color: rgb(0, 0, 0);">
<b>Abstract: </b></div>
<div class="elementToProof" style="font-family: Tahoma, Geneva, sans-serif; font-size: 12pt; color: rgb(0, 0, 0);">
Deep neural networks have drawn much attention due to their success in various vision tasks, including classification. Class Incremental Leaning is a paradigm where instances from new object classes are added sequentially. Traditional methods are faced with
catastrophic forgetting, where the updated model forgets the old classes and focuses only on the new classes. In this work, we introduce a framework called incremental PPCA for class incremental learning. It uses a self-supervised pre-trained feature extractor
to obtain meaningful features and trains Probabilistic PCA models on the extracted features for each class separately. The Mahalanobis distance is used to obtain the classification result, and an equivalent equation is derived to make the approach computationally
affordable. Experiments on standard and large datasets show that the proposed approach outperforms existing state-of-the-art incremental learning methods by a large margin. The fact that the model is trained on each class separately makes it applicable to
training on very large datasets such as the whole ImageNet with more than 10,000 classes. To better handle so many classes, we take inspiration from our understanding of the human hierarchical cognition models and propose a framework called Hierarchical PPCA
for image classification. The framework uses probabilistic PCA models as basic classification units and groups the image classes into a smaller number of super-classes. During classification, Hierarchical PPCA assigns a sample to a small number of most likely
super-classes, and restricts the image classification to the image classes corresponding to these super-classes. Experiments on ImageNet indicate the hierarchical classifier can achieve a 4-16 times speedup compared to a standard classifier without any loss
in accuracy.</div>
<div style="font-family: Tahoma, Geneva, sans-serif; font-size: 12pt; color: rgb(0, 0, 0);">
<br>
</div>
<div class="elementToProof" style="font-family: Tahoma, Geneva, sans-serif; font-size: 12pt; color: rgb(0, 0, 0);">
Additional colloquium details can be found here,</div>
<div class="elementToProof" style="font-family: Tahoma, Geneva, sans-serif; font-size: 12pt; color: rgb(0, 0, 0);">
<a href="https://nam04.safelinks.protection.outlook.com/?url=https%3A%2F%2Fwww.sc.fsu.edu%2Fnews-and-events%2Fcolloquium%2F1856-colloquium-with-adrian-barbu-2025-02-5&data=05%7C02%7Csc-seminar-announce%40lists.fsu.edu%7Cee7743f828d5455dbf6b08dd4219d171%7Ca36450ebdb0642a78d1b026719f701e3%7C0%7C0%7C638739400828250929%7CUnknown%7CTWFpbGZsb3d8eyJFbXB0eU1hcGkiOnRydWUsIlYiOiIwLjAuMDAwMCIsIlAiOiJXaW4zMiIsIkFOIjoiTWFpbCIsIldUIjoyfQ%3D%3D%7C0%7C%7C%7C&sdata=tlbwAdWOnLV7V4xAFp46%2Fry0oPtj%2BUstueyZFqglsmM%3D&reserved=0" originalsrc="https://www.sc.fsu.edu/news-and-events/colloquium/1856-colloquium-with-adrian-barbu-2025-02-5" shash="NdepQ8JV87XXzkf4tI2S0KwAJshHUFfSCIXm6hy0XLBIhXz087kzt9LYhbNzXGLYx+92bRNZbHNBHNbRCR1uFEfSTa8da7M3KWcdXnEhZ6P3YewKuLKbPLLlVhk0EOx6kIvYlkVSMUn5O1zqAgpqTaZ5Vt+PRyeM0uvqx+ylgwA=" id="OWAbf4a60ed-5814-5b13-6203-bf7fc8fa6a52" class="OWAAutoLink">https://www.sc.fsu.edu/news-and-events/colloquium/1856-colloquium-with-adrian-barbu-2025-02-5</a></div>
<div class="elementToProof" style="font-family: Tahoma, Geneva, sans-serif; font-size: 12pt; color: rgb(0, 0, 0);">
<br>
</div>
</body>
</html>